---
title: "Xinyang Han — papers of 2025 — 2 papers, the most cited first"
description: "Xinyang Han — papers of 2025: 2 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/xinyang-han/year/2025/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xinyang-han/year/2025/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Xinyang Han](https://md.research.elamur.ai/free/en/authors/xinyang-han/) / 2025

# Xinyang Han — papers of 2025 — 2 papers, the most cited first

2 papers · [all years of Xinyang Han](https://md.research.elamur.ai/free/en/authors/xinyang-han/#years)

**[AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender](https://md.research.elamur.ai/free/en/papers/zhao-2025-adasteer-your-aligned-llm-is/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.*2025 · 11 citations*

**[Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs](https://md.research.elamur.ai/free/en/papers/zhao-2025-beware-your-po-measuring-mitigating/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Weixiang Zhao, Yulin Hu, Yang Deng, et al.*2025 · 9 citations*